Clinical Image Analysis @ OSU-BMI

European PhD students visiting CIALAB

2011-07-05T09:43:00.001-07:00

Onur Yorulmaz and Alexander Suhre have joined the CIA Lab from June to August 2011. Both of them are graduate students from Bilkent University, Ankara, Turkey under the supervision of Dr. A. Enis Cetin. Their visit is funded by the EC as part of the MIRACLE project. Onur will be studying possible application areas of grouplets to microscopic images. Alexander will apply some image classification algorithms that were developed in his previous research to follicular lymphoma image data.

New Computer-aided Follicular Lymphoma Image Analysis Research Publications

2011-05-18T11:18:00.000-07:00

Two papers from the CIALAB have been accepted for publication in the IEEE Transactions on Medical Imaging and Computerized Medical Imaging and Graphics. The abstracts are below.

Partitioning Histopathological Images: An Integrated Framework for Supervised Color-Texture Segmentation and Cell Splitting

Kong, H.; Gurcan, M.; Belkacem-Boussaid, K.;

ABSTRACT

For quantitative analysis of histopathological images, such as the lymphoma grading systems, quantification of features is usually carried out on single cells before categorizing them by classification algorithms. To this end, we propose an integrated framework consisting of a novel supervised cell-image segmentation algorithm and a new touching-cell splitting method. For the segmentation part, we segment the cell regions from the other areas by classifying the image pixels into either cell or extra-cellular category. Instead of using pixel color intensities, the color-texture extracted at the local neighborhood of each pixel is utilized as the input to our classification algorithm. The color-texture at each pixel is extracted by local Fourier transform (LFT) from a new color space, the most discriminant color space (.. ). The .. color space is optimized to be a linear combination of the original RGB color space so that the extracted LFT texture features in the .. color space can achieve most discrimination in terms of classification (segmentation) performance. To speed up the texture feature extraction process, we develop an efficient LFT extraction algorithm based on image shifting and image integral. For the splitting part, given a connected component of the segmentation map, we initially differentiate whether it is a touching cell clump or a single non-touching cell. The differentiation is mainly based on the distance between the most likely radial symmetry center and the geometrical center of the connected component. The boundaries of touching-cell clumps are smoothed out by Fourier shape descriptor before carrying out an iterative, concave-point and radial-symmetry based splitting algorithm. To test the validity, effectiveness and efficiency of the framework, it is applied to follicular lymphoma pathological images, which exhibit complex background and extracellular texture with non-uniform illumination condition. For comparison purposes, the results of the proposed segmentation algorithm are evaluated against the outputs of Super-pixel, Graph-Cut, Mean-shift, and two state-of-the-art pathological image segmentation methods using ground-truth that was established by manual segmentation of cells in the original images. Our segmentation algorithm achieves better results than the other compared methods. The results of splitting are evaluated in terms of under-splitting, over-splitting, and encroachment errors. By summing up the three types of errors, we achieve a total error rate of 5.25% per image.

Automatic detection of follicular regions in H&E images using iterative shape index

Belkacem-Boussai, K.; Samsi, S.; Lozanski, G.; Gurcan,M.N.;

ABSTRACT

Follicular Lymphoma (FL) accounts for 20–25% of non-Hodgkin lymphomas in the United States. The first step in grading FL is identifying follicles. Our paper discusses a novel technique to segment follicular regions in H&E stained images. The method is based on three successive steps: (1) region-based segmentation, (2) iterative shape index (concavity index) calculation, (3) and recursive watershed. A novel aspect of this method is the use of iterative Concavity Index (CI) to control the follicular splitting process in recursive watershed. CI takes into consideration the convex hull of the object and the closest area surrounding it. The mean Zijbendos similarity index (ZSI) final segmentation score on fifteen cases was 78.33%, with a standard deviation of 2.83.

CIALAB featured in Ohio Supercomputer Center Center Press Release

2011-02-08T13:06:00.000-08:00

CIALAB's work on Follicular Lymphoma for faster and more consistent diagnoses was recognized in a press release by the Ohio Supercomputer Center. The full article can be found at http://www.osc.edu/press/releases/2011/lymphoma.shtml

Research on Digital Pathology published in Journal of Pathology Informatics

2011-01-20T13:02:00.000-08:00

Barriers and facilitators to adoption of soft copy interpretation from the user perspective: Lessons learned from filmless radiology for slideless pathology

Emily S Patterson¹, Mike Rayo¹, Carolina Gill², Metin N Gurcan³

^{¹ Division of Health Information Management and Systems, School of Allied Medical Professions, College of Medicine, The Ohio State University, Columbus, OH 43210, USA
² Department of Industrial, Interior and Visual Communication Design, The Ohio State University, Columbus, OH 43210, USA
³ Department of Biomedical Informatics, The Ohio State University, Columbus, OH 43210, USA}

^{Background: Adoption of digital images for pathological specimens has been slower than adoption of digital images in radiology, despite a number of anticipated advantages for digital images in pathology. In this paper, we explore the factors that might explain this slower rate of adoption. Materials and Method: Semi-structured interviews on barriers and facilitators to the adoption of digital images were conducted with two radiologists, three pathologists, and one pathologist's assistant. Results: Barriers and facilitators to adoption of digital images were reported in the areas of performance, workflow-efficiency, infrastructure, integration with other software, and exposure to digital images. The primary difference between the settings was that performance with the use of digital images as compared to the traditional method was perceived to be higher in radiology and lower in pathology. Additionally, exposure to digital images was higher in radiology than pathology, with some radiologists exclusively having been trained and/or practicing with digital images. The integration of digital images both improved and reduced efficiency in routine and non-routine workflow patterns in both settings, and was variable across the different organizations. A comparison of these findings with prior research on adoption of other health information technologies suggests that the barriers to adoption of digital images in pathology are relatively tractable. Conclusions: Improving performance using digital images in pathology would likely accelerate adoption of innovative technologies that are facilitated by the use of digital images, such as electronic imaging databases, electronic health records, double reading for challenging cases, and computer-aided diagnostic systems.}

CIALAB Hosts International Visitor

2010-11-29T06:45:00.001-08:00

Dr. Philippe Belhomme is visiting CIALAB from CAEN, France. During his visit Dr. Belhomme will be available to provide valuable input on the lab's current research projects.

Biomedical Imaging Specialist joins CIALAB

2010-11-01T06:37:00.000-07:00

Dr. Hatice Cinar Akakin has joined the Clinical Image Analysis group as a Biomedical Imaging Specialist. Dr. Cinar Akakin received her BS and MS degrees in Electrical and Electronics Engineering Department of Eskisehir Osmangazi University and Anadolu University, in 2000 and 2003 respectively. She got her PhD degree from Electrical and Electronics Engineering Department of Bogazici University, Turkey, in 2010. She was a teaching and research assistant at Bogazici University, Signal and Image Processing Laboratory (BUSIM) from 2004 to 2010. During her PhD, she got experience in developing algorithms for face image analysis from low level image processing to high level interpretations.

Dr. Cinar Akakin’s research interests are in the areas of computer vision, image and video analysis and machine learning.

Metin Gurcan Elected to Editorial Board of JPI

2010-10-13T12:18:00.000-07:00

Metin Gurcan, Associate Professor of BMI, has been elected to the editorial board of the Journal of Pathology Informatics ( http://www.jpathinformatics.org/). The Journal of Pathology Informatics (JPI) is an open access peer-reviewed journal dedicated to the advancement of pathology informatics. This is the official journal of the Association for Pathology Informatics (API). The journal aims to publish broadly about pathology informatics and freely disseminate all articles worldwide. This journal is of interest to pathologists, informaticians, academics, researchers, health IT specialists, information officers, IT staff, vendors, and anyone with an interest in informatics.

Amie Draper has been awarded a Choose Ohio First Scholarship

2010-09-20T07:40:00.001-07:00

Undergraduate student Amie Draper has received a Choose Ohio First Scholarship through the Ohio Bioinformatics Consortium for the 2010-2011 academic year.

The program is aimed towards providing both undergraduate and graduate students who are interested in pursuing careers in bioinformatics or related fields with scholarships and educational opportunities. Scholarships are awarded to those who demonstrate academic excellence and a strong interest in computation and biology/chemistry.

Best Paper Award at ICPR 2010 to CIALAB researchers

2010-09-02T11:46:00.000-07:00

A paper by Clinical Image Analysis Lab (CIA-LAB) researchers, Drs Gurcan and Sertel, in collaboration with Indiana University-Purdue University Indianapolis has received the best paper award in Bioinformatics and Biomedical Applications track at the International Conference on Pattern Recognition. The paper entitled “A Multiple Instance Learning Approach toward Optimal Classification of Pathology Slides” competed with other 2140 papers for this recognition. The award-winning paper deals with histopathological image analysis of breast-cancer tissues with the aid of computers.

The CIA-LAB at the Department of Biomedical Informatics (www.bmi.osu.edu/cialab ) designs and develops algorithms, tools, techniques for the computer-assisted analysis and interpretation of medical images.

Jeff Prescott has received his PhD in Biomedical Engineering.

2010-07-23T07:53:00.000-07:00

Thesis Title: Computer-Assisted Discovery and Characterization of Imaging Biomarkers for Disease Diagnosis and Treatment Planning

Abstract:

The rapid growth of diagnostic medical imaging studies has led to enormous strides in the effective diagnosis and treatment of myriad diseases, from chronic diseases to life threatening cancers. The rise of imaging as a major factor in medical decision making has directly led to a drive towards quantification of image findings, in order to augment the qualitative analysis of trained medical professionals, such as radiologists. The overarching goal of this dissertation is to explore, develop, and evaluate imaging biomarkers for both chronic and life threatening diseases. Towards this goal, this dissertation has the following two aims:

1. Discover and characterize imaging biomarkers for diseases which may have either acute/sub-acute presentation or treatment, or diseases which may have a more chronic course and treatment intervention. The former analysis is focused on the case of cervical cancer, and the latter is focused on osteoarthritis (OA).

2. Apply digital image processing methods to the acquired images which leverage the spatial information in the images to characterize the anatomy, physiology, and pathophysiology of a disease process.

These aims were designed to improve the characterization of human disease by extracting quantifiable information from the acquired medical images. For the case of cervical cancer, analyses were undertaken of higher order statistics and texture measures as features to be used in the classification of cervical cancer tumor volumes in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) as either likely to recur or be controlled after treatment. The contributions of these analyses are:

1. A physiologically-meaningful measure of tumor vascularity by using the wavelet decomposition to quantify texture, which predicts the outcome of radiation treatment at two-year post-treatment follow-up with 100% accuracy, based on early treatment DCE-MRI studies of the tumor.

2. The demonstration of texture measures as more important than change in tumor volume for accurate treatment outcome prediction.

For the case of OA, analyses were undertaken of the quadriceps muscle morphology (cross-sectional area (CSA)) and content (intramuscular adipose tissue (IAT)), femur morphology, and meniscus morphology (volume) on MRI as potential biomarkers for OA severity. The analyses of the quadriceps muscle and the femur were further pursued through the development of semi-automated and automated segmentation procedures. The findings and contributions of these analyses are:

1. The association of the CSA of a particular muscle in the quadriceps, the vastus intermedius, with a reduced risk of more severe radiographic OA.

2. The finding that quadriceps lean muscle CSA (anatomical muscle CSA minus IAT) is associated with sex, age, and BMI, which are risk factors for OA.

3. The volume of the lateral meniscus has multiple significant associations with the volume of the tibial articular cartilage in subjects with OA.

4. The development of an image enhancement procedure which standardizes the intensities in MRI images between all subjects and allows for the efficient and accurate structure segmentation and imaging biomarker calculation.

5. The development of a semi-automated segmentation algorithm for the individual quadriceps muscles, using atlases and level set contour evolution.

6. A comparison of atlas segmentation procedures, demonstrating that the use of multiple atlases is superior to the use of “representative” atlases selected by a trained human reader.
The use of medical imaging allows for the non-invasive localization and characterization of disease, which is especially important for diseases which have significant short-term mortality (such as cancer) or long-term morbidity (such as OA). By studying diseases at these two ends of the spectrum, a unique understanding of the imaging biomarker development and evaluation process can be gained. In addition, the application of digital image processing methods can improve the characterization of the imaging manifestations of disease by providing consistent, accurate, and complicated quantification techniques, which may be difficult, or impossible, for human readers to provide.

Research on Follicular Lymphoma accepted for publication in TBME Letters

2010-07-20T15:26:00.000-07:00

CIALAB research on the detection of follicles in follicular lymhpoma has been accepted for publication in TBME Letters. Information regarding the publication is found below:

Title: Detection of Follicles from IHC Stained Slides of Follicular Lymphoma Using Iterative Watershed

Authors: Siddharth Samsi, Gerard Lozanski, Arwa Shana'ah, Ashok K Krishanmurthy, Metin N. Gurcan

Abstract: Follicular Lymphoma (FL) is one of the most com- mon types of non-Hodgkin Lymphoma in the United States. Diagnosis of FL is based on tissue biopsy that shows characteristic morphologic and immunohistochemical findings. Our group’s work focuses on development of computer-aided image analysis techniques to improve FL grading. Since centroblast enumeration needs to be performed in malignant follicles, the development of an automated system to accurately identify follicles on digital images of lymphoid tissue is an important step. In this paper we describe an automated system to identify follicles in IHC stained tissue sections. A unique feature of the system described here is the use of texture and color information to mimic the process that a human expert might use to identify follicle regions. Comparison of system-generated results with expert-generated ground truth has shown promising results, with a mean similarity score of 87.11%.

Research accepted for publication in special issue of IEEE Transactions on Biomedical Engineering

2010-07-08T12:08:00.000-07:00

CIALAB research on developing an automated computer-assisted system for follicular lymphoma grading has been accepted for publication in IEEE Transactions on Biomedical Engineering's forthcoming special issue on Multi-Parameter Optical Imaging and Image Analysis. Information regarding the publication is below:

Title: Computer-aided Detection of Centroblasts for Follicular Lymphoma Grading using Adaptive Likelihood based Cell Segmentation

Authors: Sertel O, Lozanski G, Shana'ah A, Gurcan MN

Abstract: Follicular lymphoma (FL), is one of the most common lymphoid malignancies in the western world. FL has a variable clinical course and important clinical treatment decisions for FL patients are based on histological grading, which is done by manually counting the large malignant cells called centroblasts (CB) in ten standard microscopic high power fields from H&E-stained tissue sections. This method is tedious and subjective; as a result suffers from considerable inter- and intra-reader variability even when used by expert pathologists. In this study, we present a computer-aided detection system for automated identification of CB cells from H&E-stained FL tissue samples. The proposed system uses a unitone conversion to obtain a single channel image that has the highest contrast. From the resulting image, which has a bi-modal distribution due to the H&E-stain, a cell-likelihood image is generated. Finally, a two-step CB detection procedure is applied. In the first step, we reduce evident non-CB cells based on size and shape. In the second step CB detection is further refined by learning and utilizing the texture distribution of non-CB cells. We evaluated the proposed approach on 100 region of interest images extracted from ten distinct tissue samples and obtained a promising 80.7% detection accuracy.

Olcay Sertel has received his PhD in Electrical and Computer Engineering. He has accepted a position at BioImagene in Sunnyvale, California.

2010-06-29T12:23:00.000-07:00

Thesis Title: Image Analysis for Computer-Aided Histopathology

The main goal of this dissertation is to understand and address the challenges associated with the development of image analysis techniques for the computer-aided interpretation of high-resolution histopathology imagery. We aim to design algorithms for key image analysis tasks such as robust and adaptive segmentation of cytological components for higher level processing, construction of biologically relevant and computationally tractable features and their mathematical representations in order to differentiate distinct tissue sub-types, detection of prognostically significant tissue structures, and spatial alignment of tissue sections prepared with different stains in order to incorporate complementary in-formation.

Further information on BioImagene can be found at http://www.bioimagene.com

Dr. Sufyan Ababneh will be presenting two papers at the EIT conference

2010-03-18T09:23:00.000-07:00

Two papers have been accepted for oral presentation and inclusion in the Proceedings of 2010 IEEE International Conference on Electro/Information Technology (EIT 2010), to be held at Illinois State University, Normal, Illinois, USA, May 20-22, 2010.

Dr. Sufyan Ababneh will be presenting the following two papers at the EIT conference.

First paper:
An Automated Content-Based Segmentation Framework: Application to MR Images of Knee for Osteoarthritis Research

Second paper:
An Efficient Graph-Cut Segmentation for Knee Bone Osteoarthritis Medical Images

Dr. Gurcan is associate editor of a special issue on Whole Slide Microscopy Analysis

2010-01-29T12:48:00.000-08:00

Recent advances in technological solutions for automated high-speed and high-resolution whole slide imaging (WSI) have set the basis for a digital revolution in microscopy. This ability to observe and analyze entire specimens rather that single microscopic fields of view is affecting the way microscopic evaluation is practiced. However, WSI outputs quite huge multiple channel (at least three color channels) images (e.g. 30-40 GB) for a single slide and managing such amount of data is a unique challenge for this new era of digital microscopy. Currently, WSI workstations are mainly used to perform virtual microscopy, the practice of converting entire glass slides into high-resolution digital slides that can be viewed and managed across networks.

The aim of the proposed special issue is to present some of the cutting-edge works currently being done in Whole Slide Imaging and reveal the challenges that still lie ahead. The special issue will be a mix of invited and solicited papers. A perspective editorial written by the special issue guest editors will introduce the technology; describe potential applications and pitfalls. Invited papers are intended to provide reviews both from the medical and the image processing sides.

Further information can be found at: http://greyc.stlo.unicaen.fr/lezoray/CMIG-CFP/

CIALAB research is featured in OSU Research News

2010-01-26T06:15:00.000-08:00

Our work on the segmentation of meniscus is featured in today’s OSU Research News. CIALAB is committed to developing state-of-the art image analysis techniques to help physicians and medical researchers. The article can be read the at the following address: http://researchnews.osu.edu/archive/kneesegment.htm

Dr. Gurcan to present a tutorial at IEEE ICASSP 2010

2010-01-22T06:10:00.001-08:00

Dr. Gurcan will present a tutorial at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2010 entitled “Biomedical Image Processing and Analysis Techniques.” ( http://www.icassp2010.org/Tutorial_03.asp)

Biomedical image processing and analysis requires coordinated efforts of medical professionals, algorithmic and software engineers, and statisticians. Basic image processing techniques are frequently used in every aspect of the development from initial pre-processing techniques for noise reduction, to segmentation of lesions, to registration of lesions. Recent advances in hardware and software have made it possible to create digital scans of whole slides. These images are relatively large (100k x 100k) and in color, hence processing them present new challenges. Similarly, new computed tomography and magnetic resonance imaging scanners produce thousands of slices of images. The processing need for these images are enormous. Although biomedical image analysis research is getting increasingly popular, it does not receive sufficient coverage in most curriculums. This tutorial will introduce the current challenges and recent advances and innovations in this newly developing area while reviewing several frequently used image processing techniques in this context. It will be taught from the perspective of a researcher, who carried out biomedical image analysis and processing research for over 10 years both in academia and industry.

While most images can be easily processed using a high-end computer, very large scale microscopic images require special processing techniques. This tutorial will talk about virtual microscopy, cluster/grid computing and parallel processing techniques. Some novel computational architectures such as general purpose GPUs and cell blades (e.g. those in Sony PlayStation™ 3) are extremely suitable to process these types of images, however, they require special coding techniques. It will also discuss how some of microscopic image processing can be done using these novel computational architectures, which can also be used for efficient processing of all kinds of images.

CIALAB research is featured in The Lantern

2010-01-11T07:07:00.000-08:00

CIALAB’s Osteoarthritis research is featured in The Lantern, The Ohio State University’s student newspaper. The full article can be found here: http://www.thelantern.com/campus/researchers-awarded-2-5-million-in-grants-1.1008026

The CIALAB develops unique imaging biomarkers for the detection, diagnosis, prognosis and treatment of diseases.

Dr. Gurcan's Research Grant in OSU Research News

2009-12-21T08:23:00.001-08:00

Dr. Gurcan's EUREKA (Exceptional, Unconventional Research Enabling Knowledge Acceleration) grant is discussed in a recent OSU research news article (http://researchnews.osu.edu/archive/2009eurekagrants.htm). Dr. Gurcan's Clinical Image Analysis Lab (www.bmi.osu.edu/cialab) is committed to developing imaging biomarkers for several diseases.

Classification of centroblast cells in follicular lymphoma method accepted for publication in the Analytical and Quantitative Cytology and Histology

2009-12-04T13:43:00.000-08:00

A method for the classification of Centrablast cells versus Non-Centroblast in Follicular Lymphoma has been accepted for publication in the Analytical and Quantitative Cytology and Histology journal. The authors of the paper were Kamel Belkacem-Boussaid, Ph.D, and Michael. Pennell, Ph.D, Gerard. Lozanski, MD, Arwa. Shanaah, MD, and Metin Gurcan, Ph.D. The title of the manuscript is "Computer-aided classification of centroblast cells in follicular lymphoma". The abstract of the manuscript appears below.

Objective:
In this paper, we develop a novel automated method to distinguish centroblast (CB) cells from non-centroblast (non-CB) cells in follicular lymphoma cases and measure its performance on cases obtained by a consensus of six pathologists.

Study Design:
Geometric and color texture features were used in the training and testing of the supervised quadratic discriminant analysis (QDA) classifier. The technique was trained and tested on a data set composed of 218 CB images and 218 non-CB images. Computer performance was tested by measuring sensitivity and specificity among cells classified as centroblasts and non-centroblasts by consensus of six board-certified hematopathologists.

Results and Conclusion:
Automated classification distinguished centroblast cells (CB) from non-centroblast cells (non-CB) with a classification accuracy of 82.56% and sensitivity and specificity were 86.67% and 86.96%, respectively, when the approach was tested. The novelty of our approach is the identification of the CB cells with prior information, and the introduction of the principal component analysis (PCA) in the spectral domain to extract texture color features.

OSU President Dr. Gee honors CIALAB scholar

2009-12-04T10:30:00.000-08:00

The 4th Annual International Scholar Research Exposition Opening Reception took place in Bricker Hall on November 19, 2009 at The Ohio State University. Posters documenting the research efforts of visiting scholars are on display throughout November and December in the 2nd Floor Lobby of Bricker Hall.

Dr. Ahmet Alkan, an international scholar from Turkey, working at the CIALAB presented a poster at the exposition. The poster’s title is “Computerized Image Analysis of Thigh Muscles for Osteoarthritis.” President Gee and Dr. Whitacre, vice president for research, honored Dr. Alkan with a certificate.

Ahmet Alkan received his Ph.D. in Electrical & Electronics Engineering from Sakarya University in 2005. He is funded by a fellowship from The Scientific and Technological Research Council of Turkey (TÜBİTAK) in 2009. He is currently a visiting scholar in the Department of Biomedical Informatics at The Ohio State University, working with Dr. Metin N. Gurcan. His research interests include Signal Processing, Artificial Neural Networks and Biomedical Image Processing. He is an Assistant Professor in the Department of Electrical & Electronics Engineering at Kahramanmaras Sutcu Imam University/Turkey.

A new Ph.D. student joins the CIALAB

2009-11-13T08:55:00.000-08:00

Daniya Zamalieva, MS has joined the clinical image analysis group as a new Ph.D. student majoring in Computer Science and Engineering program. She received her B.S. degree in Computer Engineering in 2007 from Hacettepe University and M.S. degree in 2009 from Bilkent University, Turkey. During her graduate study, she was interested in Computer Vision and Pattern Recognition and she worked on processing and analysis of remotely sensed images. During her PhD studies, she will focus on computer-assisted diagnosis and creation of imaging biomarkers.

OAI meniscus segmentation work accepted for publication in Osteoarthritis and Cartilage Journal

2009-10-16T09:21:00.000-07:00

A method for the semi-automated segmentation of the meniscus in OAI images developed by the CIALAB Osteoarthritis Research Group has been accepted for publication in the Osteoarthritis and Cartilage Journal. The authors of the paper were Mark Swanson, a Medical Student with Roessler Scholarship, Jeff Prescott, an MD/PhD student in the lab, Thomas Best MD/PhD, Kimberly Powell, Rebecca Jackson MD, Furqan Haq PhD, and Metin Gurcan PhD. The abstract of the manuscript appears below.

Abstract:
Objective: The goal of this study was to develop an algorithm to semi-automatically segment the meniscus in a series of magnetic resonance (MR) images to use for normal knees and those with moderate osteoarthritis (OA).
Method: The segmentation method was developed then evaluated on 10 baseline magnetic resonance images obtained from subjects with no evidence, symptoms, or risk factors of knee (OA), and 14 from subjects with established knee OA enrolled in the Osteoarthritis Initiative (OAI). After manually choosing a seed point within the meniscus, a threshold level was calculated through a Gaussian fit model. Under anatomical, intensity, and range constraints, a threshold operation was completed followed by conditional dilation and post-processing. The post-processing operation reevaluates the pixels included and excluded in the area surrounding the meniscus to improve accuracy. The developed method was evaluated for both normal and degenerative menisci by comparing the segmentation algorithm results with manual segmentations from five human readers.
Results: The semi-automated segmentation method produces results similar to those of trained observers, with an average similarity index over 0.80 for normal participants and 0.75, 0.67, and 0.64 for participants with established knee osteoarthritis with Osteoarthritis Research International Society International (OARSI) joint space narrowing scores of 0,1, and 2 respectively.
Conclusion: The semi-automatic segmentation method produced accurate and consistent segmentations of the meniscus when compared to manual segmentations in the assessment of normal menisci in mild to moderate OA. Future studies will examine the change in volume, thickness, and intensity characteristics at different stages of OA.

OAI quadriceps segmentation work accepted for publication in the Journal of Digital Imaging

2009-10-14T19:10:00.000-07:00

A method for the segmentation of the quadriceps muscles in OAI images developed by the CIALAB Osteoarthritis Research Group has been accepted for publication in the Journal of Digital Imaging. The authors of the paper were Jeff Prescott, an MD/PhD student in the lab, Thomas Best MD/PhD, Mark Swanson, Furqan Haq PhD, Rebecca Jackson MD, and Metin Gurcan PhD. The abstract of the manuscript appears below.

Abstract: In this paper we present a semi-automated segmentation method for magnetic resonance (MR) images of the quadriceps muscles. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. The method only requires the input of a single point from the user inside the rectus femoris. The templates are quantitatively selected from a set of images based on modes in the patient population, namely sex and body type. For a given image to be segmented, a template is selected based on the smallest Kullback-Leibler divergence between the histograms of that image and the set of templates. The chosen template is then employed as an initialization for a level set segmentation, which captures individual anatomical variations in the image to be segmented. Images from 103 subjects were analyzed using the developed method. The algorithm was trained on a randomly selected subset of 50 subjects (25 men and 25 women) and tested on the remaining 53 subjects. The performance of the algorithm on the test set was compared against the ground truth using the Zijdenbos similarity index (ZSI). The average ZSI means and standard deviations against two different manual readers were: rectus femoris, 0.78 ± 0.12; vastus intermedius, 0.79 ± 0.10; vastus lateralis, 0.82 ± 0.08; vastus medialis, 0.69 ± 0.16.

Meniscus research featured on docguide.com

2009-10-12T18:53:00.000-07:00

New research on the meniscus performed by the Osteoarthritis Research Group in the CIALAB and presented at the OARSI conference was highlighted in an article on docguide.com.

CIALAB members Dr. Kamel Belkacem-Boussaid and Jeff Prescott have had their recent work accepted for presentation at SPIE 2010

2009-10-07T13:20:00.000-07:00

CIALAB members Dr. Kamel Belkacem-Boussaid and Jeff Prescott have had their recent work accepted for presentation at SPIE 2010, taking place February 13-18 in San Diego, California. The accepted papers are:

1- K. Belkacem-Boussaid, J. Prescott, G. Lozanski, and M. Gurcan, “ Segmentation of follicular regions on H&E slides using a matching filter and active contour model”

ABSTRACT: Follicular Lymphoma (FL) accounts for 20-25% of non-Hodgkin lymphomas in the US. The first step in follicular lymphoma grading is the identification of follicles. The goal of this paper is to develop a technique to segment follicular regions in H&E stained images. The method is based on a robust active contour model in which the centroid of the expanded curve is selected manually by the user. The novel aspect of this method is the introduction of matched filter for the flattening of background in the L channel of the Lab color space. The performance of the algorithm was tested by comparing it against the manual segmentations of trained readers using the Zijbendos similarity index. The mean accuracy of the final segmentation compared to the manual ground truth is 0.71 and with a standard deviation of 0.12.

2- J. Prescott, F. Haq, T.M. Best, R. Jackson, and M. Gurcan, “An analysis of methods for the selection of atlases for use in medical image segmentation”

ABSTRACT: The use of atlases has been shown to be a robust method for segmentation of medical images. In this paper we explore different methods of selection of atlases for the segmentation of the quadriceps muscles in MR images, although the results are pertinent for a wide range of applications. First, a set of readers were assigned the task of selecting atlases from a training population of images which were felt to be representative subgroups of the total population. This task was performed with no external knowledge besides the end goal of segmentation. Second, the same readers were given a subset of the training population stratified into modes of the population from which to select templates. Finally, every image in the training set was employed as an atlas, with no input from the readers, and the atlas which had the best initial registration, judged by an appropriate registration metric, was used in the final segmentation procedure. The results show that, for four out of five readers, the inclusion of modal information into the atlas selection process improved the final segmentation. However, the use of every image in the training set as an atlas far outperformed the manual atlas selection method, whether with or without modal information.

The CIALAB members would like to thank all their collaborators for their help in producing these papers.

Dr. Gurcan has been awarded an ACS Grant

2009-10-07T13:11:00.000-07:00

Dr. Gurcan has been awarded an American Cancer Society Ohio Division Supported Pilot Grant for beginning researchers to engage in basic, clinical, or behavioral/cancer control research. For this project entitled "Computer-aided clinical image analysis for cutaneous lymphomas," Dr. Gurcan will work with Drs. Porcu, Wong and Pennell to develop a system to analyze cutaneous lymphomas.
http://www.cancer.org/docroot/COM/content/div_OH/COM_7_2x_Ohio_Grant_Recipients.asp.

This project is part of Dr. Gurcan’s ongoing efforts to produce accurate and reproducible tools to distinguish discrete subsets of human cancers and to standardize measurements of response after therapy, which are essential for translational and clinical research.

Biomedical Imaging Specialist joins the Clinical Image Lab

2009-09-11T09:04:00.000-07:00

Dr. Sufyan Ababneh has joined the clinical image analysis group as a Biomedical Imaging Specialist. Dr. Ababneh received his BS degree in Electrical and Computer Engineering (ECE) from Jordan University of Science and Technology and his MS Degree in ECE from the University of Alabama in Huntsville. In 2008, he received his PhD degree in ECE from the University of Illinois in Chicago. Prior to that, he was a professional working for several well known companies in the private sector. Prior to joining the Ohio State University, he worked from 2002 to 2006, as a senior developer at Toshiba Medical Research Institute USA Inc and Bio-Imaging Research Inc developing CT-Scan imaging systems. From 1998 to 2002, he served as a senior software engineer at Motorola Inc. From 1997 to 1998, he worked as a Development Consultant for Bio-Imaging Research Inc. From 1995 to 1997, he worked as an Algorithms Developer designing embedded-systems applications at Circuit City.

Dr. Ababneh's research interests include image analysis, segmentation, classification, 2-D and 3-D compression with applications to medical images and telemedicine, image informatics and computer-aided diagnosis. He spent five years developing high performance CT-scan bio-imaging systems in distributed and embedded environments. In addition, he conducted research on watermarking-based multimedia content authentication.

Another Summer Intern Joins the CIALAB

2009-07-29T09:05:00.000-07:00

CIALAB is pleased to introduce another intern Emine Doganay working through summer’09.

Emine Doganay: I am a graduate student in Electrical and Electronics Engineering Department at Fatih University, Istanbul, Turkey. I just started my summer internship in the Clinical Image Analysis Laboratory at The Ohio State University. I am interested in learning about medical image processing and image analysis. As part of my graduate studies, for the last six month, I have been developing automated detection algorithms (computer-aided diagnosis) to recognize hypertensive patients from digital fundus images. For this summer, I have decided to join a group that is working in the medical imaging area. Therefore, I am really happy to be here. I am sincerely grateful to the Ohio State University that has given me this chance and to be a member of excellent group of professionals studying about the medical image processing area. And also I would like to thank to Dr. Gurcan for his help and support.

CIALAB Neuroblastoma Research to be presented in 2009 MICCAI Workshop

2009-07-26T17:01:00.000-07:00

CIALAB Neuroblastoma research is going to be presented in 2009 MICCAI workshop on Optical Tissue Image Analysis in Microscopy, Histopathology and Endoscopy (OPTIMHisE) which will be held in Imperial Collage, London, UK on September 24th (http://www.miccai2009.org/). The study titled "A Combined Computerized System for Classifying Digitized Whole-slide Neuroblastoma Histology: Model-based Structural Features," proposes a unified framework that combines the previously developed classification systems for the stromal development and the grade of differentiation and improves the whole-slide classification accuracy of by introducing a set of clinically driven structural features.

Olcay Sertel, Umit V. Catalyurek, Hiroyuki Shimada, and Metin Gurcan, "A Combined Computerized System for Classifying Digitized Whole-slide Neuroblastoma Histology: Model-based Structural Features".

Abstract: Neuroblastoma (NB) is one of the most malignant tumors affecting infants. In clinical practice, histopathological examination of tissue samples is required for further treatment planning. The International Neuroblastoma Pathology Committee adopted the Shimada system, which relies on several morphological characteristics of the tissue such as the degree of Schwannian stromal development and the grade of neuroblastic diﬀerentiation to categorize the tissue sample as either favorable or unfavorable histology. In this study, we presented a combined computer-aided prognosis system that integrates these two diagnosis processes within one analysis framework. Exploiting the intensity and texture characteristics of H&E-stained tissues, we achieved the segmentation using the expectation maximization (EM) algorithm that adaptively identiﬁes the distributions of the eosinophilic and basophilic structures. In addition to conventional texture features, we introduced a novel way of constructing structural features that captures the high-level perceptual patterns. The developed system was tested with an independent set of 34 whole-slide images and achieved a classiﬁcation accuracy of 94.1% (32/34).

Meniscus research to be presented at 2009 OARSI World Congress on Osteoarthritis

2009-07-21T16:00:00.000-07:00

CIALAB work detailing relationships between the meniscus and cartilage, and their implications in the development and progression of osteoarthritis, has been accepted for presentation at the 2009 OARSI World Congress on Osteoarthritis. The analysis was performed by Jeff Prescott, Furqan Haq PhD, Tom Best MD/PhD, Micheal Pennell PhD, Rebecca Jackson MD, and Metin Gurcan PhD. The full abstract appears below.

Purpose: To determine associations between meniscus volume and knee cartilage morphological measurements in subjects with osteoarthritis (OA).

Methods: All data was obtained from the Osteoarthritis Initiative’s (OAI) public use dataset (www.oai.ucsf.edu). A sample of progression subjects produced by the OAI was used for the study (Subgroup B, release 0.B.2). Out of the 160 subjects in the sample, two had no discernable meniscus and were excluded, leaving 158 subjects in the analysis. The current study focused on the right knee, as this was the only knee for which cartilage measures were available from the OAI. The lateral meniscus was manually delineated by trained readers on sagittal T2-weighted MR scans for each subject (Fig. 1). Volume measures of the anterior horn (AH), posterior horn (PH), and total meniscus were calculated using Matlab (Mathworks, Natick, MA). Cartilage morphological measurements and related bone measurements were obtained from the quantitative studies of Eckstein (kMRI_QCart_Eckstein00, release 0.1). Repeated variable measurements in the Eckstein dataset were removed, leaving only a single measurement per variable. Linear regression models were used to analyze relationships between the meniscus volume measures and the cartilage measures, with adjustments made for sex, age group (age <>= 62), and obesity (BMI <>= 30: obese). Since 92 cartilage measures were evaluated, statistical significance was assessed at a Bonferroni-correct alpha of 0.0005. All statistical analyses were performed using JMP 8.0 (SAS Institute, Cary, NC).

Results: The total volume of the meniscus has the largest number of significant associations with the cartilage measures (Table 1). All but one association between meniscus volume and cartilage measures are related to the tibia. While the majority of the lateral meniscus relationships are to the cartilage in the lateral compartment, there are a few relationships to medial compartment cartilage. The volume of the posterior horn is the only volume related to the percent of subchondral bone denuded of cartilage.

Conclusions: The results suggest that there may be an important association between the lateral meniscus and the tibia cartilage. It is interesting to note that there was no statistically significant association found between the meniscus and femur cartilage. This result implies that the tibia cartilage and lateral meniscus may respond similarly, perhaps even in unison, to changes due to OA. The current study analyzed meniscus and cartilage relationships for subjects with a wide range of radiographic and symptomatic features of OA. Further work will focus on characterization of the interactions between meniscus and articular cartilage and stratification of associations with respect to clinical measures of OA severity such as KL grade.

SREP student at CIALAB

2009-07-02T07:23:00.000-07:00

The Ohio State University Center for Clinical & Translational Science (OSU CCTS) received an NIH grant to create a Summer Research Experience Program (SREP) for high school students and teachers. This funding is part of the American Recovery and Reinvestment Act of 2009 and funds high school students and high school teachers in summer 2009. India Eaton from Eastmoor Academy has joined the CIALAB this summer as an SREP student. India is planning on attending Cleveland State University on the Honors Program scholarship. She will be majoring in mechanical engineering.

CIALAB encouraging talented young minds with summer internships

2009-06-30T10:40:00.000-07:00

CIALAB is pleased to introduce the three interns namely Tong Gan, Rosana Rodriguez Milanes and Michael Priddy working through summer’09.

Rosana Rodriguez Milanes - I am a third year undergraduate student in Electronic Engineering from Universidad del Norte, Colombia. My experience as a volunteer foreign student in the Clinical Image Analysis Laboratory has been an edifying, gratifying and enriching. Being able to participate, to learn and to collaborate in the Clinical Image Analysis Laboratory during the past two weeks has allowed me to improve my analytical and interpretative skills in processing histopathological and MRI images. I have been able to learn about segmentation, region growing, splitting and merging algorithms development. I have also had the privilege of knowing and interacting with excellent engineers who have helped me improve my skills as a foreign student. I am grateful for the opportunity that the Ohio State University has given me to collaborate and to learn with an excellent team of professionals working in the digital imaging processing field.

Michael Priddy - I am a medical student who just finished my first year. Graduating from Brigham Young University, most of my research experience has been in the field of History (which I received my undergraduate degree in). I will be spending the summer analyzing the relationships between cartilage, strength, muscle content and KL scores (osteoarthritis of the knee) with an emphasis on using the muscle content numbers (intramuscular fat content, lean muscle cross-sectional area, cross-sectional area of muscle with fat included, and the ratio of fat vs. muscle inside a muscle).

Tong Gan - I am a fourth year undergraduate student majoring in Microbiology and am interested in pursuing medical school after graduation. My research experience started with a lab assistant position in the Department of Plant and Cellular Molecular Biology of Ohio State where I learned the basics of bench research and helped various post-docs in a project discovering the basis of Circadian Rhythms in arabidopsis plants. My next research was under Dr. Thomas Best for summer credit in immunostaining rabbit muscle tissues to see the effect of massage on injured muscles. Currently, I am working on the Osteoarthritis project that entails manually segmenting the MRI medial meniscus for 160 patients and then writing a MATLAB program that measures its volume, thickness, and surface area.

Osteoarthritis muscle research to be presented at ISCIS 2009

2009-06-24T07:31:00.000-07:00

Jeff Prescott, a student in the CIALAB, has had his work accepted as a regular paper to the 24th International Symposium on Computer and Information Sciences. The work, entitled "Template-Based Level Set Segmentation using Anatomical Information: Application to Quadriceps Muscles in MR Images from the Osteoarthritis Initiative", describes a method for the semi-automated segmentation of quadriceps muscles.

Abstract: We present a preliminary evaluation of an automated segmentation method of the quadriceps muscles from MR images of the thigh. The method is being developed to assist research into morphological properties of the quadriceps muscles as biomarkers of osteoarthritis (OA) incidence and progression. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. A template image is selected using the Kullback-Leibler divergence measure based on the muscle and fat content of the thigh images. Contours of the quadriceps muscles of the chosen template are then semi-automatically registered to the image to be segmented using an affine transformation. These registered contours are used as initializations for the multi-phase level-set segmentation of the image, which is pre-processed to reduce arterial flow artifacts, the bias field, and intramuscular fat/connective tissue. Thirteen studies from eleven different subjects were analyzed. The performance was compared against manual segmentations using the Zijdenbos similarity index (ZSI). The ZSI means and standard deviations were: rectus femoris, 0.73 ± 0.13; vastus intermedius, 0.78 ± 0.09; vastus lateralis, 0.81 ± 0.14; vastus medialis, 0.85 ± 0.10.

Dr. Gurcan is a Guest Editor for IEEE Transactions on Medical Imaging for special issue on Multivariate Microscopy Image Analysis

2009-06-23T11:41:00.000-07:00

Analysis of microscopy images of samples has numerous applications in a wide range of areas such as molecular biology, life sciences, pharmacology and medicine. Recently, new protocols based on molecular labeling and imaging automation are spurring a revolution in microscopy techniques since they allow to capture the trans- or co-localization of proteins in multivariate microscopy image (MMI) data. In MMI, each pixel at a location may be associated with more than one intensity value, to an array of multiple intensities. These intensities can encode protein location, co-location or translocation over time, as seen by incident light of multiple wavelengths. In histopathology, for example, diagnosis and grading of cancer and other diseases can be improved by analyzing localization patterns in MMI obtained with multi-staining and/or multi-spectral techniques. As a consequence, there is a rapidly growing interest in the processing and analysis of MMI not only in the classic fields listed above but also in the new and rapidly evolving field of systems biology since the MMI data unfolds the spatial information on the molecular level that cannot be evaluated using the classic "omics" methods. Although there has been great progress in the development and application of image analysis in biomedicine over the recent years, there are a number of significant challenges involving the MMI data. These challenges include acquisition, efficient storage, registration, segmentation, classification, semantic annotation and visualization of the MMI data. Recent advances in other related areas such as image processing, computer vision, pattern recognition, and machine learning as well as the availability of high-performance computing equipment at a relatively affordable cost are seemingly fueling the development of computational methods to deal with these challenges.

(http://www.ieee-tmi.org/CallForPapers.html).

This Special Issue will highlight new research directions in Multivariate Microscopy Image Analysis by collecting selected papers in all relevant areas including, but not limited to, the following topics:

Registration, segmentation, classification, retrieval

Object detection/classification/quantification

Computer-aided diagnosis and grading

Visualization

System evaluation

Novel computational architectures

Other related aspects

CIALAB work accepted to EMBC 2009

2009-06-02T06:32:00.000-07:00

CIALAB members Dr. Kamel Boussaid, Dr. Erkan Mumcuoglu, Olcay Sertel, and Jeff Prescott have had their recent work accepted for presentation at EMBC 2009, taking place September 2-6 in Minneapolis, Minnesota. The accepted papers are:

Prescott JW, Swanson MS, Haq F, Best TM, Powell K, Jackson R, Gurcan MN, "An Automated Method for Femur Segmentation for Osteoarthritis Research."

Prescott JW, Priddy M, Swanson MS, Haq F, Best TM, Powell K, Jackson R, Gurcan MN, "An Automated Method for Intramuscular Fat Detection in Quadriceps Muscles for Osteoarthritis Diagnosis."

Belkacem-Boussaid K, Sertel O, Lozanski G, Shana’aah A, Gurcan MN, "Extraction of color features in the spectral domain to recognize centroblasts in histopathology."

Samsi S, Krishnamurthy AK, Groseclose M, Caprioli RM, Lozanski G, Gurcan MN, "Imaging Mass Spectrometry Analysis for Follicular Lymphoma"

Mumcuoglu EU, Prescott J, Baker BN, Clifford B, Long F, Castile R, Gurcan MN, "Image Analysis for Cystic Fibrosis: Automatic Lung Airway Wall and Vessel Measurement on CT Images"

The CIALAB members would like to thank all their collaborators for their help in producing these papers.

Dr. Gurcan's stimulus award featured in Columbus Dispatch

2009-05-18T09:05:00.000-07:00

The recent stimulus award for Dr. Metin Gurcan was featured in The Columbus Dispatch as part of an article on how stimulus funding is affecting research at The Ohio State University. The link to the article is: http://bmi.osu.edu/resources/news/stimulus_funding.pdf

Jeff Prescott awarded Jane A Blank scholarship from CSO-HIMSS

2009-05-13T14:43:00.000-07:00

CIALAB student Jeff Prescott, and MD/PhD student, has been awarded the Jane A. Blank scholarship from the Central and Southern Ohio chapter of the Healthcare Information and Management Systems Society (CSO-HIMSS).

The CSO-HIMSS Chapter annually awards the scholarship and a one-year student HIMSS membership to an undergraduate or graduate student studying in the healthcare information or healthcare management systems field.

Scholarships are awarded for academic excellence and the potential for future leadership in the healthcare information and management systems industry. Review criteria are focused on academic achievement, service activities, technical skills, career goals, demonstration of leadership potential, and communication skills.

CIALAB work to be presented at RSNA

2009-05-13T14:33:00.000-07:00

The osteoarthritis (OA) group at CIALAB has had their work accepted for presentation at RSNA's Reading Room 2009. The meeting will provide an opportunity for the group to present its software suite for analyzing medical images for exploring factors in OA severity. The suite consists of a semi-automated meniscus segmentation method developed by Mark Swanson, an MD student, and an automated quadriceps muscle segmentation method developed by Jeff Prescott, and MD/PhD student.

Tutorials of the meniscus and quadriceps segmentation procedures can be viewed at http://bmi.osu.edu/~cialab/meniscussegment.php and http://bmi.osu.edu/~cialab/thighsegment.php. The proper viewing of these videos requires Internet Explorer 6+.

CIALAB Follicular Lymphoma research to be published in the Computer Methods and Programs in Biomedicine Journal

2009-04-30T08:04:00.000-07:00

The article entitled "Feature-Based Registration of Histopathology Images with Different Stains: An Application for Computerized Follicular Lymphoma Prognosis" has been accepted for publication in the Computer Methods and Programs in Biomedicine Journal. This study is a part of the computer-aided system being developed for the automated histopathological evaluation of Follicular Lymphoma, one of the most common type of lymphoid malignancy affecting more than fifty thousand people in the United States annually. The abstract of this study appears below:

Feature-Based Registration of Histopathology Images with Different Stains: An Application for Computerized Follicular Lymphoma Prognosis

Follicular lymphoma (FL) is the second most common type of non-Hodgkin’s lymphoma. Manual histological grading of FL is subject to remarkable interand intra-reader variations. A promising approach to grading is the development of a computer-assisted system that improves consistency and precision. Correlating information from adjacent slides with different stain types
requires establishing spatial correspondences between the digitized section pair through a precise nonrigid image registration. However, the dissimilar appearances of the different stain types challenges existing registration methods.
This study proposes a method for the automatic nonrigid registration of histological section images with different stain types. This method is based on matching high level features that are representative of small anatomical structures. This choice of feature provides a rich matching environment, but also results in a high mismatch probability. Matching confidence is increased
by establishing local groups of coherent features through geometric reasoning. The proposed method is validated on a set of FL images representing different disease stages. Statistical analysis demonstrates that with a proper feature set, the accuracy of automatic registration is comparable to manual registration.

A CIALAB member graduated in winter 2009

2009-04-09T08:57:00.000-07:00

Shunmugam Mohan is a graduate student from the Department of Electrical Engineering. He joined the BMI imaging lab and started working with Dr.Gurcan from Winter 2008. His primary areas of research are Medical Image Processing, Signal Processing and Digital Communications. His Masters project was based on developing an ImageJ plugin for Haralick 3D texture analysis. He worked with Olcay Sertel on Content based Unsupervised Image Classification of Lymphoma images. He also worked with Jeff Prescott in the segmentation of MR images of patients with osteoarthritis. He has also developed websites for the CIALAB and the upcoming HIMA conference. He received his Bachelor of Engineering in Electronics and Communications Engineering from the Anna University, India.

CIALAB member has won Medical Center Research Day Travel Award

2009-04-06T08:34:00.001-07:00

With his poster presentation entitled "Histopathological Image Analysis", Olcay Sertel, a member of the Clinical Image Analysis Lab,won a travel award at the Ohio State University Medical Center Research Day, held on April 2nd. Research Day is an annual event featuring the biomedical research of trainees within the OSU Medical Center. Held each spring, Research Day features a poster display, with a judging and presentation of awards for outstanding research, as well as presentations on current topics by world renowned researchers and experts in the field of biomedical science.

Of the 304 research trainees participating in the 2008 event, 31 were chosen to receive awards. The 2008 Research Day award winners included one undergraduate student, five postdoctoral trainees, three residents or clinical fellows, 11 graduate students, ten medical students, and one MD/PhD(Medical Scientist) student. These trainees each received a travel award,which will allow them to attend and present their research at a scientific meeting of their choice.

8th Annual OSU Medical Center Research day poster presentation

2009-03-30T12:05:00.000-07:00

Research Day is an annual event featuring the biomedical research of trainees within the OSU Medical Center. This group includes graduate, undergraduate, medical and MD/PhD students of the OSU College of Medicine, as well as postdoctoral fellows and researchers and clinical residents and fellows. Held each spring, Research Day features a poster display, with a judging and presentation of awards for outstanding research, as well as presentations on current topics by world renowned researchers and experts in the field of biomedical science.

The following candidates from the CIALAB will be presenting their articles on the First Floor of the Biomedical Research Tower(460 W 12th Avenue, Columbus, OH) on April 2, 2009.

1) Olcay Sertel - HISTOPATHOLOGICAL IMAGE ANALYSIS

2) Jeffrey Prescott - COMPUTERIZED MUSCLE SEGMENTATION FOR OSTEOARTHRITIS RESEARCH

3) Siddharth Samsi - PROTEOMIC ANALYSIS OF FOLLICULAR LYMPHOMA FOR AUGMENTING COMPUTER AIDED DIAGNOSIS: A PRELIMINARY STUDY

4) Mark Swanson - A SEMI-AUTOMATED SEGMENTATION METHOD TO ASSESS THE MENISCUS IN OSTEOARTHRITIC KNEES USING MRI

CIALAB students have work accepted to OSU's Hayes Graduate Research Forum

2009-03-03T06:30:00.000-08:00

Jeff Prescott, an MD/PhD student in the CIALAB, has had his recent research work accepted to the OSU Hayes Graduate Research Forum in the Engineering area. The accepted abstract, entitled, "Computerized muscle segmentation for osteoarthritis research," describes a method for the automated segmentation of the quadriceps muscles using a template-based level set approach. The segmentations are meant to be used in the analysis of the Osteoarthritis Initiative imaging dataset for biomarkers of OA incidence and progression.

Siddharth Samsi, a PhD student in the CIALAB also had his work accepted to the OSU Hayes Graduate Research Forum in the Engineering area. The abstract, entitled "A New Image of Cancer: Protein Signatures", describes the potential of utilizing Mass Spectrometry and image analysis for the diagnosis and grading of Follicular Lymphoma.

The Hayes Graduate Research Forum is meant to "recognize outstanding graduate student scholarship within the University" and consists of paper or poster presentations for students whose abstracts are accepted to the competition.

Biomedical Imaging Specialist joins the Clinical Image Lab

2009-02-27T11:43:00.000-08:00

Dr. Kamel Belkacem-Boussaid has joined the clinical image analysis group as biomedical imaging specialist. Dr.Belkacem-Boussaid has worked in both academia and industry prior joining the image analysis group.

Dr. Belkacem-Boussaid received his BS degrees in Electrical Engineering from University of Algiers, Algeria and his MS in Electrical Engineering from University of Valeneciennes, France and Ph.D degrees in Electrical Engineering from University Pierre and Marie Curie France. From October 1997-March 2000, I was a post doctoral research associate at Beckman institute, University of Illinois at Urbana-Champaign. Prior joining Ohio State University in February 2009, he worked as senior research scientist and senior research engineer for several high-tech companies specializing in CAD systems and digital asset management software. Most recently, he was senior research scientist at Bioimagene, a Biotechnology company in which he was in charge of the design and development of new algorithms for the analysis of tissue biopsies and as well as image quality improvement and assessment of the bioimagene scanner images.

Dr. Belkacem-Boussaid research interests focus on filtering, segmentation, image quality, multi-modals registrations, image analysis, pattern recognition, 3-D reconstruction and analysis, and digital signal processing applied to medicine. In the past twelve years he was involved in the development of computer aided detection and diagnosis (CAD) systems for different organs such as; retina, breast, prostate, brain, and knee using different modalities.

Dr. Belkacem-Boussaid is a senior IEEE member and a member of SPIE.

Dr. Gurcan has been awarded a patent

2009-02-13T09:18:00.000-08:00

Metin Gurcan, PhD, an Assistant Professor of Department of Biomedical Informatics, has been awarded a patent, US# 7,486,812 by the United States Patent and Trademark Office. The patent, entitled, “Shape estimates and temporal registration of lesions and nodules,” covers methods for the automated segmentation and registration of lung nodules from computed tomography images of lung. This is the second patent awarded to Dr. Gurcan, whose first patent (US # 7,236,620) covers methods in detecting early signs of colon cancer from virtual colonoscopy studies.

Dr. Gurcan's research interests include image analysis and understanding, computer vision with applications to medicine. Over the last decade, his research contributions have concentrated on computer-aided detection and diagnosis (CAD) of cancer. He has developed CAD systems for different organs such as breast, lung and colon and for different modalities such as mammography and CT. CAD development requires interdisciplinary research. Therefore, Dr. Gurcan's research experience covers a wide variety of interrelated fields such as multi-resolution image decomposition, adaptive filtering, statistical pattern recognition, neural networks, image and volume registration, morphological image processing, multi-dimensional optimization, image segmentation, and statistical signal processing.

Dr. Gurcan is the recipient of the British Foreign and Commonwealth Organization Award, Children’s Neuroblastoma Cancer Foundation Young Investigator Award and National Cancer Institute’s caBIG Embodying the Vision Award. Further information on Dr. Gurcan’s research can be found on the Clinical Image Analysis Lab web page (http://www.bmi.osu.edu/~cialab).

CIALAB Hosting Fulbright Scholar

2009-02-06T07:42:00.000-08:00

The OSU Department of Biomedical Informatics Clinical Image Analysis (CIA) Lab is hosting Dr. Erkan Mumcuoglu as a Fulbright visiting professor. Dr. Mumcuoglu is an Associate Professor of Medical Informatics at Middle East Technical University, Ankara, Turkey. He is also among the founders of the same department.

Dr. Mumcuoglu's main research interest is Medical Image Analysis: segmentation, registration, computer-aided diagnosis and content-based image retrieval. His Ph.D. degree is from University of Southern California on statistical PET image reconstruction algorithms and modeling. Dr. Mumcuoglu has been collaborating with Dr. Metin Gurcan from our department in the segmentation of retinal mitocondria on electron-microscopy images.

Dr. Mumcuoglu is going to give a talk on his research actvities on Feb. 12 at 4 pm as part of the departmental Research In Progress (RIP) Seminar Series.

2009-02-05T08:41:00.000-08:00

CIALAB Neuroblastoma research to be published in the Pattern Recognition Journal

The article entitled, "Computer-aided prognosis of neuroblastoma onwhole-slide images: Classification of stromal development" has been accepted for publication in the Special Issue on Digital Image Processing and Pattern Recognition Techniques for the Detection of Cancer in Pattern Recognition, one of the most prestigious journal of the Pattern Recognition Society. This study is a part of the computerized neuroblastoma prognosis research being conducted in the CIALAB since 2007. The goal is to develop an image analysis system that will be used in clinical practice to aid pathologists. Subscribers can access the full text online at http://dx.doi.org/10.1016/j.patcog.2008.08.027. The publication abstract appears below.

Computer-aided prognosis of neuroblastoma onwhole-slide images: Classification of stromal development

We are developing a computer-aided prognosis system for neuroblastoma (NB), a cancer of the nervous system and one of the most malignant tumors affecting children. Histopathological examination is an important stage for further treatment planning in routine clinical diagnosis of NB. According to the International Neuroblastoma Pathology Classification (the Shimada system), NB patients are classified into favorable and unfavorable histology based on the tissue morphology. In this study, we propose an image analysis system that operates on digitized H&E stained whole-slide NB tissue samples and classifies each slide as either stroma-rich or stroma-poor based on the degree of Schwannian stromal development. Our statistical framework performs the classification based on texture features extracted using co-occurrence statistics and local binary patterns. Due to the high resolution of digitized whole-slide images, we propose a multi-resolution approach that mimics the evaluation of a pathologist such that the image analysis starts from the lowest resolution and switches to higher resolutions when necessary. We employ an offline feature selection step, which determines the most discriminative features at each resolution level during the training step. A modified k-nearest neighbor classifier is used to determine the confidence level of the classification to make the decision at a particular resolution level. The proposed approach was independently tested on 43 whole-slide samples and provided an overall classification accuracy of 88.4%.

CIALAB cervical cancer research to be published in the Journal of Digital Imaging

2009-01-22T10:15:00.000-08:00

Jeff Prescott, an MD/PhD student in the lab, has had his research accepted from publication in JDI. The article, entitled, "Temporal Analysis of Tumor Heterogeneity and Volume for Cervical Cancer Treatment Outcome Prediction: Preliminary Evaluation," explores the efficacy of using wavelet coefficient measures of tumor perfusion on dynamic contrast-enhanced MR images of cervical tumors to predict the outcome of radiation treatment of the tumors. Subscribers to JDI can access the full text online at http://dx.doi.org/10.1007/s10278-009-9179-7. The publication abstract appears below.

Temporal Analysis of Tumor Heterogeneity and Volume for Cervical Cancer Treatment Outcome Prediction: Preliminary Evaluation

In this paper we present a method of quantifying the heterogeneity of cervical cancer tumors for use in radiation treatment outcome prediction. Features based on the distribution of masked wavelet decomposition coefficients in the tumor region of interest (ROI) of temporal dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) studies were used along with the imaged tumor volume to assess the response of the tumors to treatment. The wavelet decomposition combined with ROI masking was used to extract local intensity variations in the tumor. The developed method was tested on a data set consisting of 23 patients with advanced cervical cancer who underwent radiation therapy; 18 of these patients had local control of the tumor and five had local recurrence. Each patient participated in two DCE-MRI studies: one prior to treatment, and another early into treatment (2 - 4 weeks). An outcome of local control or local recurrence of the tumor was assigned to each patient based on a post-therapy follow-up at least 2 years after the end of treatment. Three different supervised classifiers were trained on combinational subsets of the full wavelet and volume feature set. The best performing linear discriminant analysis (LDA) and support vector machine (SVM) classifiers each had mean prediction accuracies of 95.7%, with the LDA classifier being more sensitive (100% vs. 80%) and the SVM classifier being more specific (100% vs. 94.4%) in those cases. The K-nearest neighbor classifier performed the best out of all three classifiers, having multiple feature sets that were used to achieve 100% prediction accuracy. The use of distribution measures of the masked wavelet coefficients as features resulted in much better predictive performance than those of previous approaches based on tumor intensity values and their distributions or tumor volume alone.

Keywords: cervical cancer, treatment outcome prediction, dynamic contrast enhanced MRI, wavelet.

Research Updates at the Clinical Image Analysis Lab

2008-12-17T11:53:00.000-08:00

Metin Gurcan is organizing a special session workshop to be held in Paris, France as part of the IEEE's ISBI conference. Further information: http://www.dcs.warwick.ac.uk/research/mimic/chip_isbi08/
Jun Kong, Olcay Sertel and Jeff Prescott will be presenting at SPIE's Medical Imaging Conference (http://spie.org/medical-imaging.xml) to be held in San Diego, CA , Feb. 16-21, 2008. The papers to be presented:

Prescott J, Donqing Z, Wang J, Mayr N, Yuh W, Saltz J, Gurcan MN, Cancer treatment outcome prediction by assessing temporal change: Application to cervical cancer, Accepted to SPIE Medical Imaging 2008, 16 - 21 February 2008, San Diego, California.
Sertel O, Kong J, Lozanski G, Catalyurek U, Saltz J, Gurcan MN, Computerized microscopic image analysis of follicular lymphoma, Accepted to SPIE Medical Imaging 2008, 16 - 21 February 2008, San Diego, California.
Sertel O, Kong J, Shimada H, Catalyurek U, Saltz J, Gurcan MN, Computer-aided prognosis of neuroblastoma: classification of stromal development on whole-slide images, Accepted to SPIE Medical Imaging 2008, 16 - 21 February 2008, San Diego, California.
Kong J, Sertel O, Shimada H, Boyer K, Saltz J, Gurcan MN, A multi-resolution image analysis system for computer-assisted grading of neuroblastoma differentiation, Accepted to SPIE Medical Imaging 2008, 16 - 21 February 2008, San Diego, California.

Jeffrey Prescott will be presenting at SIIM meeting (http://www.siim2008.org/>) to be held in Seattle, WA, May 15-18, 2008. Jeff won an award with his paper (http://bmi.osu.edu/news_detail.php?id=82 ). The paper to be presented:

Prescott J, Zhang D, Wang J, Mayr N, Saltz J, Gurcan MN, Outcome Prediction for Radiation Treatment of Cervical Cancer by Assessing Tumor Heterogeneity and Temporal Change, Accepted to SIIM 2008, May 15-18, 2008, Seattle, WA.

Olcay Sertel will be presenting at the ICASSP meeting (http://www.icassp2008.org/) to be held in Las Vegas, NV, March 30-April 4, 2008. The paper to be presented:

Sertel O, Kong J, Catalyurek U, Lozanski G, Shanaah A, Saltz J, Gurcan MN, Texture classification using nonlinear color quantization: Application to histopathological image analysis, Accepted to ICASSP 2008, March 30-April 4, 2008, Las Vegas, NV.

Olcay Sertel will be presenting at the USCAP meeting () to be held in Denver, CO, March 1-7, 2008. The paper to be presented:

Sertel O, Kong J, Lozanski G, Shana'ah A, Gewirtz A, Racke F, Zhao J, Catalyurek U, Saltz J, Gurcan MN, Computer-assisted grading of follicular lymphoma: High grade differentiation, USCAP 2008, March 1-7, 2008, Denver, CO.

An article from our group has been accepted to the Archives of Pathology and Laboratory Medicine:

Kong J, Sertel O, Shimada H, Boyer K, Saltz J, Gurcan MN, Computer-assisted grading of neuroblastic differentiation, Archives of Pathology & Laboratory Medicine, Accepted, 2008.

An article from our group has been accepted to the International Journal of Data Mining and Bioinformatics:

Ruiz A, Sertel O, Ujaldon M, Catalyurek U, Saltz J, Gurcan MN, Pathological image analysis using the GPU: Stroma classification for Neuroblastoma, International Journal of Data Mining and Bioinformatics, accepted, 2008.

An article from our group has been accepted to the Journal of Digital Imaging:

Erdal S, Catalyurek U, Payne P, Kamal J, Saltz J, Gurcan MN, A Knowledge-Anchored Integrative Image Search and Retrieval System, Journal of Digital Imaging, in print, 2008.

2008-12-17T11:47:00.000-08:00

Metin Gurcan